Skip to content
BSWEN
Blog

How to Use The Agency AI Agents with Claude Code, Cursor, and Aider

Cowrie
Cowrie
Dev @ Bswen

I’ve been using AI coding assistants for a while now, but I kept running into the same problem: every time I needed a specialized task done, I had to write detailed prompts explaining exactly what I wanted. Want a code review? Write a prompt. Need SEO analysis? Write another prompt. Backend architecture advice? You guessed it—another prompt.

Then I discovered The Agency’s collection of specialized AI agents, and everything changed. These are pre-configured agent personalities designed for specific tasks like frontend development, backend architecture, SEO analysis, code review, and more. The problem? I had no idea how to actually use them with my existing tools.

Let me show you exactly how to install and use these agents with your favorite AI coding assistant.

The Installation Options

The Agency agents support multiple AI coding tools, and the installation process depends on which one you’re using.

If you’re using Claude Code, installation is incredibly simple. Just copy the agent files to your Claude Code configuration directory:

Clone the repository
git clone https://github.com/msitarzewski/agency-agents.git
cd agency-agents
Copy agents to Claude Code directory
cp -r agency-agents/* ~/.claude/agents/

That’s it. The agents are now available in your Claude Code sessions.

Option 2: Cursor, Aider, Windsurf, Copilot

For other tools, you’ll need to use the provided conversion scripts:

Clone and enter the repository
git clone https://github.com/msitarzewski/agency-agents.git
cd agency-agents
Generate tool-specific formats
./scripts/convert.sh
Install to auto-detected tools
./scripts/install.sh

Or target a specific tool:

Install to specific tool
./scripts/install.sh --tool cursor
./scripts/install.sh --tool aider
./scripts/install.sh --tool windsurf
./scripts/install.sh --tool copilot

Option 3: Use as Reference

Each agent file is self-contained and well-documented. You can simply read them and use the prompts as reference for any AI assistant, even if there’s no automated installation available for your tool.

How to Activate Agents

Once installed, using the agents is straightforward. You just reference them by name in your AI session:

  • “Activate the Frontend Developer and help me build a React component”
  • “Use the SEO Specialist to analyze my meta tags”
  • “Act as the Backend Architect and review my API design”
  • “Apply the Code Reviewer agent to this PR”
  • “Help me as the Growth Hacker to plan user acquisition”

The agents work transparently—no special commands or syntax needed. Just mention the agent name, and the AI will adopt that specialist’s perspective and approach.

Why This Matters

I think the real value here is consistency. When I activate the Code Reviewer agent, I get the same thorough review approach every time. No need to remember all the things I want checked—the agent already knows to look for security issues, performance problems, code style, and best practices.

Here’s what I’ve gained:

  • Immediate productivity: No prompt engineering required—just activate and go
  • Consistent quality: The same specialist delivers the same approach every time
  • Tool flexibility: Works with whatever AI assistant I’m already using
  • Easy customization: I can fork the agents and modify them for my specific needs

What’s Inside

The repository includes agents for various specializations:

  • Frontend Developer
  • Backend Architect
  • Code Reviewer
  • SEO Specialist
  • Growth Hacker
  • DevOps Engineer
  • And more…

Each agent has been crafted with specific prompts and behaviors tailored to their domain. The Backend Architect thinks about scalability, the Frontend Developer focuses on UX and performance, the SEO Specialist knows about meta tags and search optimization.

Getting Started

If you’re ready to try this yourself:

  1. Clone the repository
  2. Choose your installation method based on your tool
  3. Start a session and mention an agent by name
  4. Watch as the AI adopts that specialist’s approach

The agents have made my workflow significantly more efficient. Instead of crafting detailed prompts for every task, I just activate the right specialist and get to work.

Final Words + More Resources

My intention with this article was to help others share my knowledge and experience. If you want to contact me, you can contact by email: Email me

Here are also the most important links from this article along with some further resources that will help you in this scope:

Oh, and if you found these resources useful, don’t forget to support me by starring the repo on GitHub!

Comments

Tags: